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

    Neuronpedia

    INDEX
    Explanations

    expressions containing the word "form"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe various forms of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     teasp
    -0.80
     Zup
    -0.76
    wu
    -0.73
    kees
    -0.73
    doms
    -0.72
    stones
    -0.72
     Adin
    -0.72
    ween
    -0.70
    bats
    -0.70
    nets
    -0.69
    POSITIVE LOGITS
     accommodation
    0.92
     harassment
    0.83
     discrimination
    0.77
     human
    0.74
     resistance
    0.74
     life
    0.73
     consciousness
    0.73
     coercion
    0.72
     activism
    0.72
     medi
    0.71
    Act Density 0.072%

    No Known Activations