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

    Neuronpedia

    INDEX
    Explanations

    words related to people or objects actively doing something or being in a certain state

    oai_token-act-pair · gpt-3.5-turbo

    gerund forms of verbs or verbs in their present participle form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sponge
    -0.59
     shell
    -0.57
     Hernandez
    -0.57
     Skydragon
    -0.56
    arij
    -0.55
     fert
    -0.54
     towel
    -0.54
    inem
    -0.54
     Mes
    -0.54
     Tomb
    -0.52
    POSITIVE LOGITS
    tons
    0.99
     havoc
    0.95
    eers
    0.86
    eer
    0.83
    enance
    0.81
    theless
    0.80
    forward
    0.73
    ails
    0.71
    forth
    0.71
    rarily
    0.70
    Act Density 0.233%

    No Known Activations