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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "from" indicating sources or origins in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itivity
    -0.82
    ifix
    -0.74
    hyde
    -0.71
    seek
    -0.71
    enary
    -0.70
    hops
    -0.70
    finals
    -0.70
    stakes
    -0.69
    hop
    -0.68
    ratulations
    -0.66
    POSITIVE LOGITS
     afar
    1.25
     whence
    0.96
     thence
    0.92
     inception
    0.82
     obscurity
    0.77
     1967
    0.74
     standpoint
    0.73
     perspective
    0.73
     2001
    0.72
     conception
    0.72
    Act Density 0.029%

    No Known Activations