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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to making something easier or more appealing

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accessibility and affordability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     moratorium
    -0.57
    usalem
    -0.57
     malice
    -0.55
    aldo
    -0.53
    ©¶æ
    -0.53
     Declaration
    -0.53
     clarification
    -0.53
    ahs
    -0.52
    orah
    -0.52
    ignt
    -0.52
    POSITIVE LOGITS
     enough
    0.96
     compared
    0.92
    ly
    0.84
    isable
    0.83
    ible
    0.83
    izable
    0.82
    nell
    0.78
     indeed
    0.77
     nonetheless
    0.76
    aneously
    0.76
    Act Density 0.198%

    No Known Activations