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

    Neuronpedia

    INDEX
    Explanations

    actions or tasks outlined in a step-by-step format

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to actions or steps to achieve certain goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    +.
    -0.69
    .''.
    -0.64
    usercontent
    -0.59
     Travels
    -0.58
    .�
    -0.58
    signed
    -0.58
    .''
    -0.57
    ãģ®å
    -0.57
    !.
    -0.56
    perty
    -0.55
    POSITIVE LOGITS
     properly
    0.77
     further
    0.76
     fullest
    0.69
    uate
    0.69
     truly
    0.68
     purposes
    0.65
     deeper
    0.63
     analogy
    0.62
     this
    0.60
    erning
    0.60
    Act Density 0.188%

    No Known Activations