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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "refer" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cffff
    -0.68
    herical
    -0.65
    oppable
    -0.64
    urity
    -0.63
     whiff
    -0.60
     stride
    -0.60
     foothold
    -0.59
    alach
    -0.57
     stacked
    -0.56
     anch
    -0.56
    POSITIVE LOGITS
    rers
    0.80
    entious
    0.80
    irect
    0.77
    ãĥĥ
    0.72
    itatively
    0.70
     queries
    0.68
     thereto
    0.68
    ragon
    0.67
    geon
    0.66
     questions
    0.65
    Act Density 0.014%

    No Known Activations