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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions or feelings directed at others

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

    toward and similar prepositions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iastes
    -0.30
     Entsche
    -0.30
     especias
    -0.30
     uș
    -0.28
    ([^
    -0.28
     laim
    -0.28
    Boolean
    -0.28
     lös
    -0.27
     Eſ
    -0.27
     canst
    -0.27
    POSITIVE LOGITS
     envers
    0.92
    égard
    0.84
    AndEndTag
    0.75
     gegenüber
    0.70
     confronti
    0.69
     noDo
    0.66
     égard
    0.64
     Toward
    0.62
     vů
    0.62
    toward
    0.62
    Act Density 0.033%

    No Known Activations