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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating conditions or requirements for actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.73
    ArrowToggle
    -0.69
     invokingState
    -0.68
    Izvori
    -0.67
    MLLoader
    -0.64
    WebControls
    -0.63
     quæ
    -0.63
    Portale
    -0.63
    Hochspringen
    -0.62
    Rujukan
    -0.61
    POSITIVE LOGITS
    \{\\
    0.71
    enough
    0.56
    verhält
    0.54
    然
    0.54
    amon
    0.54
    omos
    0.53
     merit
    0.53
     enough
    0.52
    хол
    0.51
     permit
    0.50
    Act Density 0.051%

    No Known Activations