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

    Neuronpedia

    INDEX
    Explanations

    adverbs with a positive connotation

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that describe actions or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ilater
    -0.89
    afety
    -0.82
     GOODMAN
    -0.72
     hemor
    -0.70
    irlf
    -0.69
     Annotations
    -0.67
     Julio
    -0.64
     burgl
    -0.63
    anian
    -0.63
     Commissioners
    -0.63
    POSITIVE LOGITS
    puff
    0.88
    rics
    0.87
    aqu
    0.86
    zed
    0.84
    tics
    0.81
    ffe
    0.80
    bane
    0.77
     impressed
    0.73
    clad
    0.72
    zza
    0.71
    Act Density 0.036%

    No Known Activations