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

    Neuronpedia

    INDEX
    Explanations

    specific words indicating roles or functions in a context typically involving individuals and their actions or attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OLON
    -0.20
    ONTAL
    -0.15
    legg
    -0.15
    èįī
    -0.14
    AMB
    -0.14
    pulse
    -0.14
    impan
    -0.14
     AAA
    -0.14
     Amb
    -0.14
    onu
    -0.14
    POSITIVE LOGITS
    avia
    0.17
    avr
    0.17
    chl
    0.16
     Hanson
    0.15
    loth
    0.15
    žila
    0.15
    eti
    0.15
    cia
    0.15
    aro
    0.15
    urch
    0.14
    Act Density 0.027%

    No Known Activations