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

    Neuronpedia

    INDEX
    Explanations

    prefixes "un-" indicating negation or reversal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usch
    -0.15
    ì£Ħ
    -0.15
     Woodward
    -0.15
    elementType
    -0.15
    akah
    -0.14
    ieves
    -0.14
    jom
    -0.14
    otate
    -0.14
    à¥Įर
    -0.14
    zo
    -0.14
    POSITIVE LOGITS
     pleasant
    0.17
     sustainable
    0.17
     Barg
    0.16
     wanted
    0.15
     lic
    0.15
     healthy
    0.15
     digest
    0.15
    bridge
    0.15
     Digest
    0.15
     controlled
    0.14
    Act Density 0.032%

    No Known Activations