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

    Neuronpedia

    INDEX
    Explanations

    words related to informal conversation or colloquial expressions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    SourceChecksum
    -1.01
    fromnode
    -0.84
    })();
    -0.81
    bootstrapcdn
    -0.80
    +#+#
    -0.78
     Normdatei
    -0.76
    OGND
    -0.75
     Paglinawan
    -0.74
    Eksterne
    -0.72
    tempted
    -0.72
    POSITIVE LOGITS
     уж
    0.59
    τοι
    0.57
    K
    0.57
     کور
    0.56
     so
    0.55
     like
    0.55
     likes
    0.55
     K
    0.54
     more
    0.53
     much
    0.51
    Act Density 0.055%

    No Known Activations