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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the letter 'G' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _ASSUME
    -0.15
    ancock
    -0.15
    ¥¤
    -0.14
    ekten
    -0.14
    ckill
    -0.14
    ãĥĥãĤ°
    -0.14
    ture
    -0.14
    .hxx
    -0.14
    ambiguous
    -0.14
    tement
    -0.14
    POSITIVE LOGITS
    illian
    0.30
    wend
    0.29
    areth
    0.28
    erald
    0.26
    ail
    0.25
    avin
    0.25
    reg
    0.25
    regor
    0.24
    aby
    0.24
    raham
    0.24
    Act Density 0.040%

    No Known Activations