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

    Neuronpedia

    INDEX
    Explanations

    verbal expressions of obligation or necessity

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

    followed by infinitive "to"

    np_acts-logits-general · gemini-2.0-flash

    to + verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Seeking
    -0.57
     pleaſure
    -0.56
     Seeking
    -0.56
    ])).
    -0.56
    ]),
    -0.55
     itſelf
    -0.55
    "]).
    -0.54
    ſelf
    -0.54
    setopt
    -0.54
    "])
    -0.53
    POSITIVE LOGITS
     get
    0.94
     go
    0.84
     got
    0.81
     put
    0.72
     gonna
    0.72
     kill
    0.71
     csin
    0.70
     gets
    0.69
     do
    0.68
     done
    0.68
    Act Density 0.780%

    No Known Activations