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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases related to encouraging actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to motivation and support for positive actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abases
    -0.69
    ynski
    -0.69
    entin
    -0.63
    arent
    -0.61
    sworth
    -0.61
     Nanto
    -0.61
    stanbul
    -0.60
    mington
    -0.59
     mole
    -0.59
    oÄŁ
    -0.58
    POSITIVE LOGITS
     Tradable
    0.77
    wcs
    0.72
    Reviewer
    0.71
     Feedback
    0.70
    untarily
    0.69
     youngsters
    0.69
    imaru
    0.67
     youth
    0.65
     experimentation
    0.64
    ========
    0.64
    Act Density 0.029%

    No Known Activations