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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating directions or paths in actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    غاÙĦ
    -0.15
    anlı
    -0.14
    asion
    -0.14
    .onActivityResult
    -0.14
    lexport
    -0.14
    beck
    -0.13
     Gül
    -0.13
    ood
    -0.13
    .Geometry
    -0.13
    erne
    -0.13
    POSITIVE LOGITS
     goes
    0.99
     go
    0.98
     went
    0.85
     Goes
    0.81
    go
    0.77
     going
    0.77
     goto
    0.76
    åİ»
    0.75
     Went
    0.70
    went
    0.69
    Act Density 0.374%

    No Known Activations