Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of personal experiences and interactions within a group context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences starting with "We" or "I" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    we experienced things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annan
    -0.60
     devenus
    -0.56
    BeginContext
    -0.55
     milliers
    -0.55
    ক্ষ
    -0.52
     anciens
    -0.52
     siècles
    -0.51
     Polisi
    -0.50
    帖最后由
    -0.49
     dapur
    -0.48
    POSITIVE LOGITS
     booked
    0.85
     ordered
    0.74
     LOVED
    0.72
    WriteTagHelper
    0.69
     loved
    0.69
     dined
    0.69
    AndEndTag
    0.69
     chofe
    0.68
    complexContent
    0.63
     ordering
    0.62
    Act Density 0.079%

    No Known Activations