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

    Neuronpedia

    INDEX
    Explanations

    phrases and verbs indicating evidence or validation of findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    innen
    -0.16
    uen
    -0.16
    awai
    -0.16
    .synthetic
    -0.15
    ulla
    -0.15
    uede
    -0.15
    anni
    -0.14
    level
    -0.14
    etto
    -0.14
    ve
    -0.14
    POSITIVE LOGITS
    caller
    0.15
    ecast
    0.15
    eson
    0.14
     ÑĢÑĥкаÑħ
    0.14
    arie
    0.14
    anced
    0.14
    ả
    0.14
    ruk
    0.14
    clas
    0.14
     array
    0.13
    Act Density 0.053%

    No Known Activations