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

    Neuronpedia

    INDEX
    Explanations

    concepts related to the act of capturing or representing ideas and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     use
    -0.49
    жды
    -0.45
    miyorum
    -0.44
    AutoField
    -0.44
     פני
    -0.44
     fede
    -0.42
    LElement
    -0.41
     am
    -0.40
     hẳn
    -0.40
     kaynağından
    -0.39
    POSITIVE LOGITS
     conveys
    0.94
     conveying
    0.91
     conveyed
    0.85
     convey
    0.81
     captures
    0.80
     Convey
    0.77
    recated
    0.76
    AnchorStyles
    0.74
     capturing
    0.74
     refleja
    0.73
    Act Density 0.286%

    No Known Activations