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

    Neuronpedia

    INDEX
    Explanations

    the verb "has" indicating possession or occurrence in various contexts

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

    mentions of specific entities taking some kind of action

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    atically
    -0.65
    eem
    -0.65
     Apart
    -0.63
    icking
    -0.60
    icks
    -0.60
    aneous
    -0.59
    ancing
    -0.59
    umping
    -0.56
    tone
    -0.56
    inkle
    -0.55
    POSITIVE LOGITS
     been
    1.31
    been
    1.02
     undergone
    1.02
    kell
    1.01
     Been
    0.96
     become
    0.94
     WATCHED
    0.92
     gotten
    0.91
    raltar
    0.91
     begun
    0.89
    Act Density 0.305%

    No Known Activations