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

    Neuronpedia

    INDEX
    Explanations

    comparisons using the structure "as...as."

    oai_token-act-pair · gpt-3.5-turbo

    comparisons and similes expressing qualities of things

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTH
    -0.69
     Cosponsors
    -0.69
    osit
    -0.69
    abis
    -0.67
    ãĤ¤
    -0.66
    UCT
    -0.66
    agents
    -0.66
    livious
    -0.65
    ":""},{"
    -0.64
    éĸ
    -0.63
    POSITIVE LOGITS
     possibly
    0.95
     Possible
    0.90
     imaginable
    0.86
     ever
    0.85
     EVER
    0.83
     possible
    0.79
     feas
    0.79
     practicable
    0.76
     conceivable
    0.74
    bler
    0.74
    Act Density 0.063%

    No Known Activations