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

    Neuronpedia

    INDEX
    Explanations

    verbs related to various types of actions such as 'captured', 'disclosed', 'quoting', 'reviewed', and 'dismissed'

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions and events involving documentation or reporting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adra
    -0.95
    adan
    -0.86
    yip
    -0.81
    pered
    -0.73
    trained
    -0.71
    asso
    -0.68
    owitz
    -0.68
    achev
    -0.68
    irlf
    -0.68
    feat
    -0.68
    POSITIVE LOGITS
     ones
    0.84
     goods
    0.84
     versions
    0.81
     Assets
    0.77
     objects
    0.76
    own
    0.74
     entities
    0.74
    paren
    0.74
     assets
    0.72
     items
    0.71
    Act Density 0.416%

    No Known Activations