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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "onto" along with related phrases conveying movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    X
    -0.81
     h
    -0.77
     r
    -0.74
    h
    -0.71
    r
    -0.71
    m
    -0.71
    E
    -0.69
    Fields
    -0.69
     m
    -0.69
    M
    -0.69
    POSITIVE LOGITS
     onto
    1.46
    onto
    1.10
     Ont
    1.03
     myſelf
    1.00
    Ont
    1.00
    ₂+
    0.98
    Cuánt
    0.96
    .}~\
    0.93
    gether
    0.93
     chofe
    0.92
    Act Density 0.071%

    No Known Activations