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

    Neuronpedia

    INDEX
    Explanations

    phrases related to attempts to contact for comments or information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating contact or communication attempts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     subp
    -0.59
    Fit
    -0.55
    comes
    -0.54
    ever
    -0.53
     aspir
    -0.52
    ãĥĻ
    -0.52
     instituted
    -0.51
     decorations
    -0.51
     preached
    -0.51
     clipboard
    -0.50
    POSITIVE LOGITS
     by
    0.78
     via
    0.74
    =-=-=-=-
    0.74
    ONSORED
    0.70
    ragon
    0.65
    OHN
    0.65
    dinand
    0.64
    via
    0.64
    By
    0.63
    heastern
    0.63
    Act Density 0.071%

    No Known Activations