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

    Neuronpedia

    INDEX
    Explanations

    proper names or entities containing the string "ka"

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "ka"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lessly
    -0.74
    orship
    -0.73
    Ö¼
    -0.73
    CLASSIFIED
    -0.68
    á½
    -0.65
    NRS
    -0.62
     surpr
    -0.62
    aments
    -0.62
    GGGGGGGG
    -0.61
    service
    -0.60
    POSITIVE LOGITS
    ichi
    1.10
    osta
    1.02
    oru
    0.87
    esthesia
    0.86
    pler
    0.86
    emon
    0.86
    uthor
    0.84
    esthetic
    0.83
    vel
    0.81
    iku
    0.81
    Act Density 0.044%

    No Known Activations