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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate predictive or speculative language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raquo
    -0.16
    ÑģÑĤвоÑĢ
    -0.15
    elles
    -0.15
    lisi
    -0.15
    abeth
    -0.14
    vore
    -0.14
    rende
    -0.14
    reno
    -0.14
    resume
    -0.14
    iete
    -0.14
    POSITIVE LOGITS
    achen
    0.15
     McInt
    0.14
    ibs
    0.14
    pyx
    0.13
    .Binding
    0.13
    hib
    0.13
    .pipeline
    0.13
    grave
    0.13
    缼
    0.13
    Europe
    0.13
    Act Density 0.004%

    No Known Activations