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

    Neuronpedia

    INDEX
    Explanations

    verbs related to physical actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    actions or commands related to physical engagement or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     namely
    -0.64
     specifying
    -0.64
     ensuring
    -0.58
    lihood
    -0.57
     ensured
    -0.55
     Reported
    -0.54
     Various
    -0.54
     doubtless
    -0.53
    MAT
    -0.53
     developing
    -0.53
    POSITIVE LOGITS
     oneself
    0.97
     yourself
    0.87
     yourselves
    0.82
    igate
    0.81
     ourselves
    0.75
    aldehyde
    0.72
    pipe
    0.72
    ulate
    0.71
    iate
    0.69
    tin
    0.69
    Act Density 0.604%

    No Known Activations