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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating collaborations or partnerships in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    adio
    -0.15
    .MATCH
    -0.14
    chet
    -0.14
    à¤Ĥà¤ļ
    -0.14
     msgid
    -0.14
    reh
    -0.14
    orable
    -0.13
    ÙĪÙĦ
    -0.13
    agher
    -0.13
     JNI
    -0.13
    POSITIVE LOGITS
    AKER
    0.16
     superClass
    0.15
    vey
    0.15
     cred
    0.14
    ain
    0.14
     Ernst
    0.13
    HAL
    0.13
    abus
    0.13
    ytt
    0.13
     Kür
    0.13
    Act Density 0.421%

    No Known Activations