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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty and unknown information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    mai
    -0.14
    éĮ²
    -0.14
    ele
    -0.14
    ATA
    -0.14
    erte
    -0.14
    aison
    -0.14
    ichick
    -0.14
    leich
    -0.14
    levard
    -0.14
    enta
    -0.13
    POSITIVE LOGITS
    exact
    0.17
     çĨ
    0.17
     exact
    0.17
    çĨ
    0.16
     exactly
    0.15
    nak
    0.15
    оки
    0.15
    etxt
    0.15
    ocop
    0.14
    undler
    0.14
    Act Density 0.073%

    No Known Activations