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

    Neuronpedia

    INDEX
    Explanations

    phrases related to loss and being left behind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Kont
    -0.18
     lightning
    -0.16
    jab
    -0.15
     Walt
    -0.15
    ONSE
    -0.14
    ellan
    -0.14
    éł
    -0.14
    BadRequest
    -0.13
    .UTC
    -0.13
    or
    -0.13
    POSITIVE LOGITS
    åѤ
    0.17
    olon
    0.16
     Colon
    0.16
    orta
    0.16
    quire
    0.15
    oren
    0.15
    alink
    0.15
    oure
    0.14
     Primer
    0.14
     vul
    0.14
    Act Density 0.264%

    No Known Activations