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

    Neuronpedia

    INDEX
    Explanations

    verbs related to completing tasks or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases or constructs related to ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    minus
    -0.76
    Course
    -0.68
    âĶĢâĶĢ
    -0.63
    æ©
    -0.63
    Pi
    -0.61
    Org
    -0.61
    furt
    -0.61
     âĶ
    -0.60
    facing
    -0.60
    DragonMagazine
    -0.59
    POSITIVE LOGITS
     Destruction
    0.72
     controversy
    0.69
     existence
    0.68
    enance
    0.66
     slain
    0.66
     brow
    0.64
    senal
    0.64
     virtues
    0.63
     Newly
    0.61
     Diseases
    0.61
    Act Density 0.705%

    No Known Activations