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

    Neuronpedia

    INDEX
    Explanations

    expressions of possibility, suggestion, and uncertainty

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

    may/might followed by want/need/find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.64
     autorytatywna
    -0.63
    UrlResolution
    -0.60
     kasarigan
    -0.60
    __':
    -0.56
    SharedDtor
    -0.56
    __':
    -0.55
     surla
    -0.55
    WriteTagHelper
    -0.54
    LLocation
    -0.52
    POSITIVE LOGITS
     wondering
    0.73
     think
    0.71
     wonder
    0.70
     wondered
    0.66
     want
    0.66
     feel
    0.63
     wish
    0.62
     consider
    0.60
     find
    0.60
     noticed
    0.59
    Act Density 0.024%

    No Known Activations