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

    Neuronpedia

    INDEX
    Explanations

    terms related to computer security and technology

    oai_token-act-pair · gpt-3.5-turbo

    fragments of incomplete or poorly structured sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ogly
    -0.67
    burn
    -0.65
     Cent
    -0.60
     equip
    -0.60
     sacrifice
    -0.59
     twins
    -0.59
    boro
    -0.58
    abwe
    -0.58
     life
    -0.58
     burn
    -0.58
    POSITIVE LOGITS
    ³³³³
    1.08
    ³³³³³³³³
    1.05
    Furthermore
    1.02
    Newsletter
    1.00
    Nevertheless
    1.00
    ³³³³³³³³³³³³³³³³
    0.99
    However
    0.97
    Regarding
    0.97
    Nonetheless
    0.95
    Additionally
    0.93
    Act Density 0.578%

    No Known Activations