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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating comparisons or contrasts between groups or entities

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     CreateTagHelper
    -0.69
    ésult
    -0.60
    tiérrez
    -0.60
    latform
    -0.60
    gorithm
    -0.59
     hyg
    -0.59
     Phry
    -0.59
     Debre
    -0.58
    iſter
    -0.58
    اهرة
    -0.57
    POSITIVE LOGITS
     utafitiHapana
    0.70
     Davison
    0.65
    __*/
    0.61
     <<<<<<<<<<<<<<
    0.60
     ModelExpression
    0.60
    GenerationType
    0.56
    ClientSize
    0.56
     &___
    0.55
     HasFactory
    0.55
    atology
    0.55
    Act Density 0.029%

    No Known Activations