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

    Neuronpedia

    INDEX
    Explanations

    phrases related to secrets or keys to success

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to secrets and keys to success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JP
    -0.79
    rive
    -0.73
    ategor
    -0.72
    NJ
    -0.71
    dain
    -0.70
    TN
    -0.69
    urses
    -0.66
    supported
    -0.65
    ãĥīãĥ©
    -0.64
    hak
    -0.64
    POSITIVE LOGITS
    iest
    1.02
    liest
    0.76
     mystery
    0.75
    ultimate
    0.74
     lurking
    0.74
     hiding
    0.73
     takeaway
    0.72
     ingredient
    0.72
     culprit
    0.71
    why
    0.71
    Act Density 0.149%

    No Known Activations