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

    Neuronpedia

    INDEX
    Explanations

    negative phrases or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .addField
    -0.16
    /epl
    -0.16
    ñ
    -0.15
    mamak
    -0.15
    scopes
    -0.15
    aad
    -0.14
    iology
    -0.14
     Hob
    -0.14
    %)↵↵
    -0.14
    LAY
    -0.14
    POSITIVE LOGITS
     disappoint
    0.20
    alama
    0.18
     False
    0.17
     Fail
    0.17
     soon
    0.17
     fail
    0.17
     disappointed
    0.16
     bad
    0.16
     limit
    0.16
     miss
    0.15
    Act Density 0.138%

    No Known Activations