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

    Neuronpedia

    INDEX
    Explanations

    the word "never" and its variations, indicating a focus on negation or the absence of an action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    :]:
    -0.85
    DispatchToProps
    -0.73
    ionage
    -0.71
     desg
    -0.70
    raszam
    -0.69
    stdc
    -0.69
     attente
    -0.69
    vidia
    -0.68
    ESD
    -0.68
    voegd
    -0.68
    POSITIVE LOGITS
     NEVER
    1.55
     Never
    1.55
     never
    1.54
    NEVER
    1.53
    Never
    1.49
    never
    1.46
     EVER
    1.26
     Nunca
    1.22
     Ever
    1.13
     ever
    1.13
    Act Density 0.067%

    No Known Activations