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

    Neuronpedia

    INDEX
    Explanations

    negations and phrases indicating conditionality or absence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    leo
    -0.16
    ouv
    -0.16
    avn
    -0.15
    á»ģn
    -0.15
     detriment
    -0.14
     McCabe
    -0.14
    ãĥį
    -0.14
     nackte
    -0.14
    criptor
    -0.14
    etch
    -0.14
    POSITIVE LOGITS
     need
    0.26
     chances
    0.25
     possibility
    0.25
     chance
    0.20
     Need
    0.20
     likelihood
    0.19
     possibilities
    0.19
     probability
    0.18
     possibilit
    0.18
    need
    0.18
    Act Density 0.069%

    No Known Activations