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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the act of referring or directing someone's attention to something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "refer" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alach
    -0.78
    ilings
    -0.64
     underdog
    -0.64
     whiff
    -0.63
     heart
    -0.63
    olean
    -0.60
     sshd
    -0.57
    cho
    -0.57
    urity
    -0.56
    illa
    -0.56
    POSITIVE LOGITS
    irect
    0.81
    entious
    0.81
    rers
    0.78
    itatively
    0.77
     Refer
    0.72
    oras
    0.71
     refer
    0.71
    ring
    0.69
    iously
    0.69
    ãĥĥ
    0.67
    Act Density 0.025%

    No Known Activations