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

    Neuronpedia

    INDEX
    Explanations

    expressions related to attitudes and reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    attitude towards, reaction to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rè
    -0.43
     täv
    -0.43
     världen
    -0.42
    Designs
    -0.42
    ckså
    -0.42
    ⎩
    -0.41
    opatho
    -0.41
     øns
    -0.41
    ніципалі
    -0.41
     BrowserModule
    -0.40
    POSITIVE LOGITS
    AxisAlignment
    0.48
    fortawesome
    0.39
    enterOuterAlt
    0.37
    attitude
    0.36
     attitude
    0.36
    IntoConstraints
    0.36
    下载附件
    0.36
     Attitude
    0.36
    Attitude
    0.36
     attitudes
    0.35
    Act Density 0.068%

    No Known Activations