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

    Neuronpedia

    INDEX
    Explanations

    co-occurrences of conjunctions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    extAlignment
    -0.81
     BoxFit
    -0.74
    ^(@)
    -0.74
     $_"
    -0.69
     Monfieur
    -0.69
    RegistryLite
    -0.68
     myſelf
    -0.66
     auffi
    -0.65
     AttributeSet
    -0.65
     localObject
    -0.65
    POSITIVE LOGITS
    /
    0.59
     !=
    0.53
     ==
    0.52
    вот
    0.49
    ®
    0.49
    var
    0.49
    TM
    0.49
    adjusted
    0.49
    ga
    0.48
    зу
    0.48
    Act Density 0.354%

    No Known Activations