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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases using the word "as."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     either
    -0.73
     very
    -0.66
    TemporalType
    -0.63
    either
    -0.63
     Very
    -0.63
     a
    -0.62
    Very
    -0.62
    oughly
    -0.59
     VERY
    -0.59
     extremely
    -0.58
    POSITIVE LOGITS
    存于互联网档案馆
    0.66
     entanto
    0.66
    ResumeLayout
    0.61
    featureID
    0.56
    aarrggbb
    0.56
    twimg
    0.56
    IntoConstraints
    0.54
    клопе
    0.53
    migrationBuilder
    0.53
    hame
    0.51
    Act Density 0.110%

    No Known Activations