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

    Neuronpedia

    INDEX
    Explanations

    statements indicating likelihood or probability of occurrence

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating likelihood or probability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Cooldown
    -0.77
    cle
    -0.73
    DAQ
    -0.72
     embodiments
    -0.71
    Textures
    -0.70
    urance
    -0.68
    cedented
    -0.68
    holder
    -0.67
    audio
    -0.66
    engineering
    -0.66
    POSITIVE LOGITS
     receive
    1.19
     participate
    1.13
     succeed
    1.12
     be
    1.10
     survive
    1.08
     engage
    1.06
     offend
    1.03
     utilize
    1.02
     indulge
    1.02
     cooperate
    1.01
    Act Density 0.067%

    No Known Activations