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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate significant political actions or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ooter
    -0.16
    INUX
    -0.14
    oot
    -0.14
     yerini
    -0.13
    اÙĬا
    -0.13
    indr
    -0.13
    (Arg
    -0.13
    itte
    -0.13
    minecraft
    -0.13
    çĩ
    -0.13
    POSITIVE LOGITS
     move
    0.86
    move
    0.66
     Move
    0.63
    -move
    0.60
     moves
    0.60
    Move
    0.58
     decision
    0.57
    _move
    0.52
     MOVE
    0.51
    .move
    0.47
    Act Density 0.360%

    No Known Activations