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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    words indicating collaborative actions or relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assian
    -0.66
    :(
    -0.66
    affle
    -0.62
    involved
    -0.59
    Poké
    -0.59
    .(
    -0.59
    .:
    -0.59
    roller
    -0.58
    heid
    -0.58
    ERO
    -0.58
    POSITIVE LOGITS
     chiefly
    1.08
     preferably
    1.02
     principally
    0.99
     mainly
    0.92
     mostly
    0.91
     especially
    0.85
     primarily
    0.85
     perhaps
    0.84
     hereby
    0.84
     annually
    0.83
    Act Density 0.203%

    No Known Activations