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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umpt
    -0.17
    ambre
    -0.17
     enim
    -0.15
    iez
    -0.15
    itos
    -0.14
    elib
    -0.14
    ellig
    -0.14
    arrass
    -0.13
    .Getter
    -0.13
    apult
    -0.13
    POSITIVE LOGITS
     correctness
    0.19
     haven
    0.18
     correct
    0.16
    esk
    0.16
    -strokes
    0.15
     disclaimer
    0.15
    woff
    0.15
     accuracy
    0.15
     vér
    0.15
    ладÑĥ
    0.14
    Act Density 0.110%

    No Known Activations