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

    Neuronpedia

    INDEX
    Explanations

    words related to geographical locations or contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    даÑħ
    -0.17
    rer
    -0.17
    shot
    -0.16
    reach
    -0.16
    rett
    -0.16
    mq
    -0.15
    dsl
    -0.15
    ré
    -0.15
    vester
    -0.15
    ForObject
    -0.15
    POSITIVE LOGITS
    iro
    0.43
    iros
    0.40
    iras
    0.36
    ira
    0.35
    IRO
    0.29
    yro
    0.29
    IRA
    0.24
    ir
    0.23
    ño
    0.23
    ños
    0.23
    Act Density 0.051%

    No Known Activations