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

    Neuronpedia

    INDEX
    Explanations

    words related to legal actions and procedures

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the substring "ct" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mandela
    -0.65
    Ô
    -0.64
     hars
    -0.61
     Soy
    -0.61
     exha
    -0.59
    hattan
    -0.59
     ghetto
    -0.58
     ANC
    -0.58
    visor
    -0.58
    Bey
    -0.57
    POSITIVE LOGITS
    ools
    1.07
    acular
    1.05
    rees
    1.04
    reme
    1.02
    uits
    1.00
    inct
    0.98
    urn
    0.97
    rix
    0.95
    ypes
    0.94
    ype
    0.94
    Act Density 0.029%

    No Known Activations