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

    Neuronpedia

    INDEX
    Explanations

    phrases ending in quotes

    oai_token-act-pair · gpt-3.5-turbo

    sentences and statements that convey conclusive thoughts or remarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     coerc
    -0.73
    gettable
    -0.70
     isolate
    -0.68
     exha
    -0.66
    undai
    -0.65
     veter
    -0.65
     lifes
    -0.65
    iliated
    -0.64
    entimes
    -0.64
    ¥ŀ
    -0.63
    POSITIVE LOGITS
     âĢķ
    1.23
    <|endoftext|>
    1.09
    ↵
    0.97
    [/
    0.96
    ↵↵
    0.95
     ~
    0.94
     –
    0.92
    >>\
    0.91
     [/
    0.91
     Said
    0.89
    Act Density 0.089%

    No Known Activations