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

    Neuronpedia

    INDEX
    Explanations

    negative prefixes and suffixes related to capability and state of being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     وتسجيلات
    -0.83
    TagMode
    -0.73
    PhysRevD
    -0.65
    CardModule
    -0.63
    PhysRevLett
    -0.63
    OGND
    -0.59
     fourrure
    -0.59
    Sortie
    -0.58
     ***!
    -0.58
     žem
    -0.56
    POSITIVE LOGITS
    mless
    1.13
    celess
    1.07
    seless
    1.04
    eless
    1.03
    hless
    1.01
    ELESS
    0.99
    lessly
    0.92
    less
    0.88
    lless
    0.85
     unbroken
    0.84
    Act Density 0.267%

    No Known Activations