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

    Neuronpedia

    INDEX
    Explanations

    negative expressions and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olley
    -0.15
    ondo
    -0.15
    Away
    -0.15
    _callbacks
    -0.15
    á¿
    -0.15
    Aceptar
    -0.15
    untime
    -0.15
    rawl
    -0.14
     اÙĦÙħÙĩ
    -0.14
    olla
    -0.14
    POSITIVE LOGITS
    leg
    0.20
     just
    0.19
     Just
    0.18
     mounts
    0.17
     short
    0.16
     mount
    0.16
     shorts
    0.16
     Shorts
    0.16
     leg
    0.16
     Short
    0.16
    Act Density 0.006%

    No Known Activations