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

    Neuronpedia

    INDEX
    Explanations

    phrases related to offering insights and assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    омен
    -0.14
     thresh
    -0.14
    大ãģį
    -0.14
    ÂĮ
    -0.14
     inherits
    -0.14
    umont
    -0.14
    .bunifuFlatButton
    -0.14
    minent
    -0.13
    ersist
    -0.13
    .swagger
    -0.13
    POSITIVE LOGITS
    ins
    0.45
    Ins
    0.41
    -ins
    0.36
     INS
    0.31
    .ins
    0.29
    INS
    0.29
    _ins
    0.29
    (ins
    0.28
     deep
    0.26
     Ins
    0.25
    Act Density 0.123%

    No Known Activations