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

    Neuronpedia

    INDEX
    Explanations

    referential phrases and familial relationships within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    __":
    -0.83
    DoubleQuotes
    -0.74
    GEBURTSDATUM
    -0.68
    awakeFromNib
    -0.61
    zyści
    -0.60
    onians
    -0.60
     swimmers
    -0.59
    __':
    -0.59
     perfons
    -0.57
    gians
    -0.57
    POSITIVE LOGITS
     former
    1.01
     best
    0.90
     ex
    0.85
     childhood
    0.80
     longtime
    0.78
    former
    0.77
    best
    0.75
     close
    0.73
     long
    0.70
     neighbor
    0.69
    Act Density 0.224%

    No Known Activations