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

    Neuronpedia

    INDEX
    Explanations

    words relating to a process of change or advancement

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "becoming."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    otropic
    -0.77
    umbo
    -0.67
    aceous
    -0.65
    gio
    -0.64
     Tactics
    -0.63
     Glover
    -0.63
    aign
    -0.63
    udge
    -0.62
    inarily
    -0.61
     Ranch
    -0.61
    POSITIVE LOGITS
     obsolete
    0.90
     embr
    0.88
     entangled
    0.85
     extinct
    0.85
     accustomed
    0.83
     experien
    0.78
     mosqu
    0.76
     embroiled
    0.76
     unemploy
    0.76
     streng
    0.76
    Act Density 0.010%

    No Known Activations