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

    Neuronpedia

    INDEX
    Explanations

    negative markers or symbols associated with data or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows hyphens or special characters

    np_acts-logits-general · gemini-2.0-flash

    type -1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pritchard
    -0.58
    (
    -0.57
     <<<<<<<<<<<<<<
    -0.56
     Kirkpatrick
    -0.56
     leverage
    -0.54
     رو
    -0.53
     McGuire
    -0.52
     van
    -0.52
     seg
    -0.51
     Driscoll
    -0.51
    POSITIVE LOGITS
    =-=-=-=-
    1.13
    *-
    1.07
    =-=-
    1.03
    *-*-
    1.03
    &-
    0.98
    .'-
    0.98
     للمعارف
    0.97
    +-+-
    0.93
    '-
    0.90
     ujednoznacz
    0.90
    Act Density 1.108%

    No Known Activations