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

    Neuronpedia

    INDEX
    Explanations

    attends to conjunctions from tokens that introduce temporal or conditional contexts

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.08
    1:0.10
    2:0.09
    3:0.12
    4:0.10
    5:0.06
    6:0.27
    7:0.16
    Negative Logits
     חיצוניים
    -0.54
     متعلقه
    -0.52
     Majefty
    -0.51
     كومونز
    -0.49
     itſelf
    -0.47
     doubtnut
    -0.47
    IVEREF
    -0.47
     виправивши
    -0.46
     Exacts
    -0.45
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
     };
    0.24
    ry
    0.23
     PropTypes
    0.23
    чется
    0.22
    allage
    0.22
     profili
    0.22
     fondi
    0.22
    帐户
    0.21
    };
    0.21
    ForeColor
    0.21
    Act Density 0.034%

    No Known Activations