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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate future intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cheon
    -0.17
    mime
    -0.15
    عÙĬØ©
    -0.15
    éĸ
    -0.14
    менÑĪ
    -0.14
    ĶĦ
    -0.14
    ç§ij
    -0.14
     رد
    -0.14
    ICA
    -0.13
    ÑĢеб
    -0.13
    POSITIVE LOGITS
    ensen
    0.16
     Swe
    0.15
     Tone
    0.15
    uture
    0.15
    ture
    0.15
     Binder
    0.14
     Hend
    0.14
    anvas
    0.14
    scratch
    0.14
     Phase
    0.13
    Act Density 0.051%

    No Known Activations